The shift to electromobility is accelerating, but combustion engines and hybrid systems remain important in sectors like light- and heavy-duty vehicles, where performance, range, or cost limitations play a major role. Optimizing diesel engine efficiency and reducing emissions is critical. However, classical physics-based 0D/1D models are computationally demanding and are hardly applicable for real-time purposes. In this study, a calibrated 1D diesel engine model is suggested for transformation into a neural network architecture to enable real-time optimization. The model divides the engine into intake, exhaust, and combustion sections, each modeled by different neural networks. One of the advantages of this modular and layered approach is the flexibility to change individual components without needing to retrain every single model. Long Short-Term Memory (LSTM) networks are used to capture transient phenomena, such as thermal inertias that arise in the combustion process and gas flow dynamics. The training data was generated by systematically varying engine speed, load, environmental conditions, and actuator settings to cover all possible operating conditions comprehensively. First tests show, the AI-based model achieves up to 97% of the accuracy of the physics-based model, but with predictions that are 300 times faster and can operate in real-time. Validation across the entire engine operation range is crucial to overcome limitations of traditional models and to ensure reliable predictions even in boundary conditions. This approach significantly improves engine development capabilities, cutting computational costs, speeding up design cycles, and reducing time-to-market, especially for advanced combustion engines and hybrid systems. Future efforts will focus on enhancing the model’s performance across a broader set of conditions and expanding the approach to full powertrain technologies.